TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

How to deliver on Machine Learning projects

162 pointsby jakekover 6 years ago

7 comments

vjscover 6 years ago
So we had this idea of a new feature for our product. The only way to quickly do it was to somehow implement a machine learning algo and that would give us the result that we wanted. Viola!! It seemed simple.<p>Now our company doesn&#x27;t have any machine learning expert or a data science genius. Going for hiring one would take time. Taking someone up on contract would be very expensive (our CEO wasn&#x27;t ready to shell out that kinda money). So the task fell on me. They asked me to go through the multitudes of Machine leaning MOOCs out there and get a working prototype ready in 2 weeks.<p>I had already done Andrew Ng&#x27;s course back when it came out for the first time. But my memory had faded for the lack of practice.<p>I re-ran the course again. I went over a couple of online ML books too.<p>Then I started thinking of the problem at hand. Unfortunately, it turned out to be a chicken and egg problem. For the feature to work perfectly we needed a large amount of training data to train our models. But without the feature actually deployed, we didn&#x27;t have any way to collect any training data.<p>So we ultimately fell back to simple algo, that took it&#x27;s decisions based on a few hard coded rules. Things have been working fine till now.
评论 #18148305 未加载
评论 #18150399 未加载
评论 #18148405 未加载
评论 #18148351 未加载
评论 #18148441 未加载
评论 #18148360 未加载
评论 #18148352 未加载
评论 #18149769 未加载
评论 #18148513 未加载
评论 #18148490 未加载
评论 #18149233 未加载
fromthestartover 6 years ago
Machine Learning is much more nuanced than people seem to understand. You can&#x27;t just throw data at a net and expect results-this field requires a heavy degree of intuition, and engineers must be prepared for nets to pick up on patterns not obvious to humans, which can lead to unintuitive results.<p>Neural nets are basically black box heuristics, with unpredictable edge cases. Much like human reasoning, I&#x27;d warrant!
b_tterc_pover 6 years ago
this doesn’t seem to offers any novel perspectives. I read it as intended for self marketing.
评论 #18148496 未加载
评论 #18148292 未加载
评论 #18147996 未加载
评论 #18148195 未加载
评论 #18151654 未加载
serenover 6 years ago
That sounds awfully close to DMAIC.<p><a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;DMAIC" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;DMAIC</a><p>Nothing wrong with that though...
sgt101over 6 years ago
So we do the loop 50 time and we now have an algorithm that works (97%!) on the test set. We are happy! We run it in production and everything looks good (prbly 92% ish). Everyone is happy! We all get promoted or get new jobs. Then, one day, someone actually looks at what it&#x27;s doing... and lo. It. does. not. work (~51%) Everyone is sad. Apart from us! Yay!<p>Seriously - an optimisation loop on a test set? Seriously?
rfeatherover 6 years ago
The point about hacking away at the code needs to be couched heavily. It&#x27;s too easy to conclude you&#x27;ve got negative or positive results when what you really have is a silly little bug. The lack of focus on implementation skills in data (or even &quot;real&quot; science) is frightful. The one take away anyone trained in software engineering could share is that if you aren&#x27;t very sure if it is working as intended, it&#x27;s very likely not. Code review is very applicable here when making major pivots, even if unit or other testing is decidedly too time consuming for the train test improve loop.<p>Edit: typo &quot;of&quot; to &quot;if&quot;. Somewhat serendipitous if you think about it.
reureuover 6 years ago
I love that &quot;Data Scientist&quot; has become such an inflated and meaningless title that now we have &quot;Machine Learning Engineer&quot;.
评论 #18149442 未加载